Navigation and Mapping

Point cloud registration and map building, 2-D and 3-D SLAM, and 2-D obstacle detection

To understand an unknown environment and navigate to a desired destination, a robot must have a clear picture of its surroundings. Especially in the absence of GPS data, a simultaneous localization and mapping(SLAM) algorithm can help a robot make effective decisions and plan a path through its environment.

SLAM consists of these two processes:

Localization — Estimating the pose of the robot in a known environment.
Mapping — Building a map of an unknown environment by using a known robot pose and sensor data.

Localization requires the robot to have a map of the environment, and mapping requires a good pose estimate. In the SLAM process, a robot creates a map of an environment while localizing itself. For more information, see Implement Point Cloud SLAM in MATLAB.

To perform SLAM, you must preprocess point clouds. Lidar Toolbox™ provides functions to extract features from point clouds and use them to register point clouds to one another. For an example of how to use fast point feature histogram (FPFH) feature extraction in a 3-D SLAM workflow for aerial data, see Aerial Lidar SLAM Using FPFH Descriptors.

You can also perform SLAM by using 2-D lidar scans. By storing the data for a 2-D lidar scan in a lidarScan object, you can perform scan matching to estimate pose. For more information, see Build Map from 2-D Lidar Scans Using SLAM.

Lidar Toolbox supports various graph-based SLAM workflows, including 2-D SLAM, 3-D SLAM, online SLAM and offline SLAM.

Functions

expand all

Detect, Extract, and Match Features

`detectLOAMFeatures`	Detect LOAM feature points from 3-D lidar data
`detectISSFeatures`	Detect ISS feature points in point cloud
`extractEigenFeatures`	Extract eigenvalue-based features from point cloud segments
`extractFPFHFeatures`	Extract fast point feature histogram (FPFH) descriptors from point cloud
`pcmatchfeatures`	Find matching features between point clouds

Register Point Clouds

`pcregisterloam`	Register two point clouds using LOAM algorithm
`pcregisterfgr`	Register two point clouds using FGR algorithm
`pcregistericp`	Register two point clouds using ICP algorithm
`pcregistercpd`	Register two point clouds using CPD algorithm
`pcregistercorr`	Register two point clouds using phase correlation
`pcregisterndt`	Register two point clouds using NDT algorithm

Estimate Pose

`matchScans`	Estimate pose between two laser scans
`matchScansGrid`	Estimate pose between two lidar scans using grid-based search
`matchScansLine`	Estimate pose between two laser scans using line features
`transformScan`	Transform laser scan based on relative pose

Build Map

`pcmaploam`	Create map of LOAM feature points for map building
`pcmapsegmatch`	Map of segments and features for localization and loop closure detection

Perform 2-D SLAM

`lidarscanmap`	Simultaneous localization and mapping using 2-D lidar scans
`addScan`	Add 2-D lidar scan to map
`detectLoopClosure`	Detect loop closure in 2-D lidar scan map
`addLoopClosure`	Add loop closure to the map
`deleteLoopClosure`	Delete loop closure between 2-D lidar scans
`poseGraph`	Create 2-D pose graph from lidar scan map
`updateScanPoses`	Update absolute poses of 2-D lidar scans
`findPose`	Find absolute pose of 2-D lidar scan in the map
`copy`	Create a copy of `lidarscanmap` object
`show`	Display 2-D lidar scans and lidar sensor trajectory

Visualize Results

`pcshowpair`	Visualize difference between two point clouds
`pcplayer`	Visualize streaming 3-D point cloud data
`pcshowMatchedFeatures`	Display point clouds with matched feature points

Sensor Model

`rangeSensor`	Simulate range-bearing sensor readings
`lidarSensor`	Simulate lidar sensor readings

Storage

`lidarScan`	Create object for storing 2-D lidar scan
`eigenFeature`	Object for storing eigenvalue-based features
`LOAMPoints`	Object for storing LOAM feature points

Topics

Implement Point Cloud SLAM in MATLAB
Understand point cloud registration and mapping workflow.
Estimate Transformation Between Two Point Clouds Using Features
This example shows how to estimate a rigid transformation between two point clouds.
Match and Visualize Corresponding Features in Point Clouds
This example shows how to match corresponding features between point clouds using the pcmatchfeatures function and visualize them using the pcshowMatchedFeatures function.
Generate Lidar Point Cloud Data for Driving Scenario with Multiple Actors
This example shows you how to generate lidar point cloud data for a driving scene with roads, pedestrians, and vehicles.

Featured Examples

Motion Compensation in 3-D Lidar Point Clouds Using Sensor Fusion

Compensate point cloud distortion due to ego vehicle motion by fusing data from Global Positioning System (GPS) and inertial measurement unit (IMU) sensors. The goal of this example is to compensate the distortion in the point cloud data and recreate the surroundings accurately.

Open Live Script

Build a Map with Lidar Odometry and Mapping (LOAM) Using Unreal Engine Simulation

Build a map with the lidar odometry and mapping (LOAM) [1] algorithm by using synthetic lidar data from the Unreal Engine® simulation environment. In this example, you learn how to:

Open Live Script

Map Indoor Area Using Lidar SLAM and Factor Graph

Implement offline lidar SLAM on collected lidar scans to map an indoor area using a factor graph and lidar scan map.

Build Map and Localize Using Segment Matching

Build a map with lidar data and localize the position of a vehicle on the map using SegMatch [1], a place recognition algorithm based on segment matching.

Open Live Script

Feature-Based Map Building from Lidar Data

Demonstrates how to process 3-D lidar data from a sensor mounted on a vehicle to progressively build a map. Such a map is suitable for automated driving workflows such as localization and navigation. These maps can be used to localize a vehicle within a few centimeters.

Open Live Script

Aerial Lidar SLAM Using FPFH Descriptors

Demonstrates how to implement the simultaneous localization and mapping (SLAM) algorithm for aerial mapping using 3-D features. The goal of this example is to estimate the trajectory of a robot and create a point cloud map of its environment.

Open Live Script

Build Map from 2-D Lidar Scans Using SLAM

Implement the SLAM algorithm on a series of 2-D lidar scans using scan processing and pose graph optimization (PGO). The goal of this example is to estimate the trajectory of the robot and build a map of the environment.

Open Live Script

Collision Warning Using 2-D Lidar

Detect obstacles and warn of possible collisions using 2-D lidar data.

Open Live Script